Eric Wang
1c6b1a513d
- prompts/collection.md: versioned collection system prompt extracted from workflow node yQaBxfrWjbRr with source/version/porting notes - llm.py: LLMService protocol; FakeLLMService (scripted, records calls); OpenAILLMService (async, wait_for timeout with cancellation, retry only on timeout/429/connection, errors normalized) - collect.py: run_collect reference impl - one LLM call produces state prefix + body, controlled repair (max 1 retry) for missing prefix or illegal stage proposal, whitelist guard, CollectReplyError without raw model content; dialogue history + confirmed fields injected into prompt so the model skips known info (作业4-5) - fields.py / clock.py: three-state field candidates (unknown/ candidate/confirmed), per-type validation (count not inferred from description, future time rejected), injectable Clock - graph.py: welcome node - first message returns fixed 1001 greeting without LLM (mirrors workflow is_first_message -> Assigned Reply#3), route empty stage to welcome - endpoints/delete_session: backend switch - langgraph clears graph checkpoint, fastgpt path unchanged - config: AGENT_LLM_PROVIDER fake|openai with validation - untrack .env (secrets), move template to root .env.example Verified: - pytest 103 passed; smoke turns 1/2/1 - Real LLM e2e: POST /chat multi-turn context works - Golden eval collection_skip_known_info: 12/12 cases pass - Golden eval no_false: 8/10 cases pass; 4 confirm/photo cases fail at final step - model routes on short reply '对' (prompt-adherence gap, photo/confirm stages are assignment 5 scope); recorded in evals/results/20261020-144856 Known limits: field extraction from model reply not wired (stub); photo/confirm nodes still scaffold; clarify counting is approximate.
86 lines
2.9 KiB
Markdown
86 lines
2.9 KiB
Markdown
# AI 事故信息采集 API（LangGraph 迁移分支）
|
||
|
||
本分支是“将对话后端从 FastGPT 工作流迁移到 LangGraph”课程的迁移准备分支。
|
||
|
||
当前状态：对外 API 契约保持不变，`/chat` 的供应商细节已封装到后端适配层（FastGPT 仍
|
||
为唯一实现），迁移计划见 [docs/langgraph-backend-migration-plan.md](docs/langgraph-backend-migration-plan.md)。
|
||
本阶段交付说明与验证证据见 [docs/assignment-baseline.md](docs/assignment-baseline.md)。
|
||
|
||
## 环境要求
|
||
|
||
- Python 3.11（使用 Conda 环境 `py3.11`，见 [AGENTS.md](AGENTS.md)）
|
||
- `fastgpt-client` SDK（当前以本地可编辑方式安装，见下文）
|
||
|
||
## 安装
|
||
|
||
```bash
|
||
conda activate py3.11
|
||
|
||
# 项目依赖
|
||
pip install -r requirements.txt
|
||
|
||
# FastGPT SDK（本地可编辑安装；SDK 源码在独立仓库维护）
|
||
pip install -e /path/to/fastgpt-python-sdk
|
||
```
|
||
|
||
## 配置
|
||
|
||
服务端通过环境变量读取 FastGPT 连接信息。复制示例配置并按环境填写：
|
||
|
||
```bash
|
||
cp .env.example .env
|
||
```
|
||
|
||
需要设置的变量：
|
||
|
||
| 变量 | 说明 |
|
||
|---|---|
|
||
| `ANALYSIS_SERVICE_URL` | FastGPT 服务地址 |
|
||
| `ANALYSIS_AUTH_TOKEN` | FastGPT API Key |
|
||
| `APP_ID` | FastGPT 应用 ID |
|
||
|
||
## 运行
|
||
|
||
```bash
|
||
python -m uvicorn src.main:app --host 127.0.0.1 --port 8000
|
||
```
|
||
|
||
- `GET /` 存活检查
|
||
- `POST /chat` 对话（`?stream=true` 为 SSE 流式）
|
||
- `POST /set_info`、`POST /get_info`、`DELETE /delete_session` 业务数据接口
|
||
|
||
## 测试
|
||
|
||
```bash
|
||
conda run -n py3.11 python -m pytest -q
|
||
```
|
||
|
||
测试分三层：
|
||
|
||
- `test/api/test_public_schema_contract.py`：公共请求/响应 schema 的契约冻结测试
|
||
- `test/api/test_chat_backend_boundary.py`：API 层与后端适配层的边界测试（fake 后端）
|
||
- `test/backends/test_fastgpt_backend.py`：FastGPT 适配器的翻译测试（fake SDK）
|
||
|
||
## 目录结构
|
||
|
||
```text
|
||
src/
|
||
api/endpoints.py # HTTP 协议层：schema、state 前缀解析、SSE 事件
|
||
backends/chat.py # 后端中立契约（ChatBackend Protocol、ChatInput/ChatResult/事件）
|
||
backends/fastgpt.py # FastGPT 适配器：SDK 调用与响应翻译
|
||
core/fastgpt_client.py # 客户端生命周期与依赖注入（lifespan）
|
||
schemas/models.py # 公共 Pydantic 模型
|
||
docs/langgraph-backend-migration-plan.md # 十阶段迁移作业计划
|
||
evals/ # 调用真实服务的评测用例与 runner
|
||
```
|
||
|
||
## 已知限制
|
||
|
||
- LangGraph 脚手架与后端适配层骨架已就位（作业 1—2）：`src/agent/`、
|
||
`src/backends/langgraph.py`、`AGENT_BACKEND` 开关；节点逻辑与适配器实现
|
||
为待完成的 TODO，对应测试 `test/agent/`、`test/backends/test_langgraph_backend.py`
|
||
在完成前会失败，属预期状态。
|
||
- `set_info` / `get_info` / `delete_session` 仍直接依赖 FastGPT 状态与历史，迁移到共享
|
||
业务状态属于作业 6。
|
||
- 服务启动需要有效的 FastGPT 配置；仅运行单元测试不需要。
|